Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add isvlasov/rageatc-oss --skill orchestrating-workgit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/isvlasov/rageatc-oss/orchestrating-work)<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/orchestrating-work"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/orchestrating-work/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/orchestrating-work"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/orchestrating-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.00964 |
| Opus 5 | $0.00019 | $0.00482 |
| Sonnet 5 | $0.00008 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
orchestrating-work scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrating Work
Execution principles for multi-agent workflows: input validation, work acceptance, file organisation, and phase transitions. Workflow structure (which phases to run) lives in designing-workflow.
1. Validate Inputs Before Invocation
Agents need complete context to work independently — every missing input costs a clarification round-trip.
Universal requirements for ALL agents (read agents/<agent-name>.md for agent-specific ones):
- Absolute path to
work/<task-id>/directory - Absolute output path for the deliverable
- All dynamic skills provided as file paths or inline content, never just names. Preloaded skills (listed in the agent's
skillsfrontmatter) are injected automatically. - All agent-specific required inputs present
- All paths absolute (no
./or../)
Before invoking: check universal requirements, read the agent's file for specific ones, then wait for the agent to echo its inputs.
If validation fails: STOP, identify and provide the missing inputs, re-validate before re-invoking. If the agent does not echo inputs: STOP — silence indicates malformed or truncated instructions; verify and re-invoke.
2. Accept or Reject Work Deliberately
Rejecting work during review costs one iteration cycle; accepting substandard work costs post-deployment rollback and rework.
Universal criteria for all artefacts:
- Output file exists at declared path; not empty or truncated
- Basic structure present; assigned task addressed completely, not partially or tangentially
- No TODO markers or placeholders (unless explicitly planned for next iteration)
- Brief requirements addressed (cross-reference the brief checklist if one exists)
Then apply artefact-type standards from the governing skill:
| Artefact type | Reference skill |
|---|---|
| Skills (SKILL.md) | writing-skills |
| Research outputs | conducting-research |
| Reviews (critic outputs) | assessing-quality |
| Briefs | creating-briefs |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 93 lines · 39 tokens per session scan A 390aa769c3ad
orchestrating-work is a skill published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 964 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
git-flow
Use when committing, branching, opening PRs, or deciding merge/branch strategy.
radin-execute
Work through a project's whole backlog: prioritize every task, execute each via a sub-agent, commit after each. Use when the user wants the entire backlog processed ("work through my backlog"), not one named task. Delegates all implementation to sub-agents; clarifies ambiguity by asking the user rather than guessing.
radin-record
Log feedback, bugs, follow-ups, or ideas raised mid-session as structured backlog entries, so they survive past the conversation. Use for /radin-record, "log this to the backlog", "add as follow-up/bug/idea", "record what we just found", "note this for later", "add findings to backlog". Triggers even on vague asks…
radin-show
Print the current project's backlog to the terminal. Use for /radin-show, "show me the backlog", "what's in the backlog", "list backlog items", "print the backlog".
run-agent
Launch and supervise Claude Code or Codex through the CCAM Run API. Use when the user wants to start a monitored agent, select a model, approval policy, sandbox, or working directory, send a follow-up, inspect live output, resume a native session, or stop a dashboard-launched run.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.